604e889ca4
- spikes/：Word 转 PDF（Gotenberg）、格式识别、原句坐标、DeepSeek 抽取四项验证代码与两版提示词；样本派生产物和 .env 不进 git - tech-validation.md：完整结论。四项都可行：WPS 字体字符集要修正并改用行高调整过的字体；格式识别不需要 Docling；表格内切句待改进；抽取需第三道依据校验与规则兜底 - architecture.md：§3.5 加预处理与字体包，§3.6 证据校验改为三道，§10 回填结论 - 03 功能需求与 decisions.md（TV1）：召回 ≥ 99%、采纳准确率 ≥ 95%、页码 100%、高亮正文 ≥ 98% / 表格 ≥ 95% Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
38 lines
2.0 KiB
Python
38 lines
2.0 KiB
Python
"""S2 对比：Docling 是否保留斜体 / 下划线。分别喂 DOCX 原文件和规范化 PDF。
|
||
用法：python -I docling_check.py <docling 地址> <docx> <pdf> <银标准 JSON>"""
|
||
import json, re, sys, time, pathlib, collections
|
||
import httpx
|
||
|
||
base, docx, pdf, silver = sys.argv[1], pathlib.Path(sys.argv[2]), pathlib.Path(sys.argv[3]), json.loads(pathlib.Path(sys.argv[4]).read_text())
|
||
OUT = pathlib.Path(__file__).parent / "out"
|
||
WS = re.compile(r"[\s ]")
|
||
silver_chars = sum(map(len, silver))
|
||
|
||
def run(path, name, extra):
|
||
t = time.monotonic()
|
||
data = {"to_formats": ["json"], "do_ocr": "false", **extra}
|
||
r = httpx.post(f"{base}/v1/convert/file", files={"files": (name, path.read_bytes())}, data=data, timeout=1800)
|
||
dt = round(time.monotonic() - t, 1)
|
||
r.raise_for_status()
|
||
doc = r.json()["document"]["json_content"]
|
||
(OUT / f"docling-{name}.json").write_text(json.dumps(doc, ensure_ascii=False))
|
||
fmt = collections.Counter(); iu = []
|
||
has_prov_bbox = 0
|
||
for item in doc.get("texts", []):
|
||
f = item.get("formatting") or {}
|
||
txt = WS.sub("", item.get("text", ""))
|
||
for k in ("bold", "italic", "underline"):
|
||
if f.get(k):
|
||
fmt[k] += len(txt)
|
||
if f.get("italic") and f.get("underline"):
|
||
iu.append(txt)
|
||
has_prov_bbox += bool(item.get("prov"))
|
||
got = Counter_overlap = sum((collections.Counter("".join(iu)) & collections.Counter("".join(silver))).values())
|
||
return {"sec": dt, "texts": len(doc.get("texts", [])), "tables": len(doc.get("tables", [])), "fmt_chars": dict(fmt),
|
||
"iu_chars": sum(map(len, iu)), "silver_iu_chars": silver_chars, "iu_char_overlap": round(got / silver_chars, 3),
|
||
"texts_with_page_bbox": has_prov_bbox}
|
||
|
||
res = {"docx": run(docx, "S06.docx", {}), "pdf": run(pdf, "S06.pdf", {"pdf_backend": "dlparse_v4"})}
|
||
print(json.dumps(res, ensure_ascii=False, indent=1))
|
||
(OUT / "docling-result.json").write_text(json.dumps(res, ensure_ascii=False, indent=1))
|